Artificial intelligence /

Detalles Bibliográficos
Clasificación:Libro Electrónico
Otros Autores: Krantz, Steven G., Rao, Arni S. R. Srinivasa, Rao, C. R.
Formato: Documento de Gobierno Electrónico eBook
Idioma:Inglés
Publicado: Cambridge, MA : Academic Press, 2023.
Colección:Handbook of statistics (Amsterdam, Netherlands) ; v. 49.
Temas:
Artificial intelligence.
Intelligence artificielle.
artificial intelligence.
Electronic books.
Acceso en línea:Texto completo
Tabla de Contenidos:
  • Intro
  • Artificial Intelligence
  • Copyright
  • Contents
  • Contributors
  • Preface
  • Part I: Foundations and methods
  • Chapter 1: Object-oriented basis of artificial intelligence methodologies
  • 1. OO in AI
  • 1.1. The concept of object
  • 1.2. Object member functions and mapping
  • 1.3. Objects in mathematics
  • 1.3.1. Object type and closure property
  • 1.3.2. Objects and mathematical spaces
  • 1.3.3. Objects in logic theory
  • 1.4. ML-Vector objects
  • 1.4.1. Nontrivial-Concept objects
  • 1.4.2. Vectorization as the first step in ML formulation
  • 1.4.3. Vector vs array
  • 1.4.4. Tensor object
  • 1.5. Objects in AI state space
  • 1.5.1. State space
  • 1.5.2. State space search
  • 1.5.2.1. Object operator
  • 1.5.2.2. Context object
  • 1.5.2.3. NEXT function
  • 1.5.2.4. Score operator
  • 1.5.3. State space search in evolutionary algorithms
  • 1.6. Derivative-type objects-Automatic differentiation
  • 2. Business requirements to ML problem formulation
  • 2.1. ML problem formulation (nonsequence types)
  • 2.2. ML formulation for sequence types
  • 2.3. Overloaded terminology
  • 2.4. Vector representation of common types of data
  • 2.4.1. Choice of the word-Tensor or vector?
  • 2.4.2. Vector representation of image
  • 2.4.3. Vector representation of univariate time series signal
  • 2.4.4. Vector representation of multivariate time series signal
  • 2.4.5. Special type of multivariate time series-Video data
  • 2.4.6. Vector representation for object detection images
  • 2.4.7. Vector representation of nonhomogeneous features
  • 2.4.8. Vector representation of text
  • 2.5. Interesting ML problem statements
  • 3. ML tools and implementation
  • 4. ML Performance monitoring
  • 5. Scope and limitation of the ML formulation
  • 5.1. Experimental set up for deductive reasoning data sets
  • 5.1.1. Data sets for selection problems
  • 5.1.2. Data sets for matching problems
  • 5.1.3. Data sets for divisibility problems
  • 5.1.4. Data sets for representation problems
  • 5.1.5. Data set for sorting problem
  • 5.1.6. Machine learning models used in the study
  • 5.1.6.1. Deep neural network
  • 5.1.6.2. Random forest
  • 5.1.6.3. Recurrent neural network
  • 5.1.7. Train and test data set partitions
  • 5.2. Observation of ML performance on deductive reasoning data sets
  • 5.3. Interesting inferences of ML on deductive reasoning problems
  • 6. Is the human brain the same as an artificial neural network?
  • 6.1. Theoretical limitation of a computer with bound on time
  • 6.2. Explainability deficit in a purely data-driven ML formulation
  • 7. Summary of the chapter
  • 8. Review questions
  • Acknowledgement
  • References
  • Chapter 2: Machine learning in physics and geometry
  • 1. Introduction and summary
  • 1.1. Mathematical data as pure data
  • 1.2. The inevitability of AI in geometry and physics
  • 2. Background physics and mathematics
  • 2.1. Polytopes

Ejemplares similares